About MCP Actions Adapter
MCP Actions Adapter converts an MCP server into an API compatible with GPT Actions. It is aimed at users who want custom GPTs to call MCP servers, and it runs from a local config file while generating an OpenAPI document to import.
Key features
- 01Converts an MCP server to a GPT Actions compatible API
- 02Uses the same config file format as Claude Desktop
- 03Serves openapi.json for import into a custom GPT
- 04Installable as a uv tool
Use cases
- 01Calling a local MCP server from custom GPT Actions
- 02Exposing a local MCP server to GPT through a Cloudflare tunnel
MCP support
The project acts as an adapter for MCP servers. It reads a Claude Desktop style config to start MCP servers and converts their capabilities into HTTP endpoints.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Actions Adapter
A simple adapter to convert a MCP server to a GPT actions compatible API
Installation
uv tool install mcp-actions-adapter
Usage
-
Create config.json the same way as claude desktop. An example config file is provided in the
config.example.jsonfile. -
Start a cloudflare tunnel with the following command:
cloudflared tunnel --url http://localhost:8000
- Start the adapter with the following command:
uv run mcp-actions-adapter -c config.json --url ${CF_TUNNEL_URL}
-
Open the custom GPT builder and copy the contents of http://localhost:8000/openapi.json into the schema box.
-
test the model
License
This project is licensed under the MIT License - see the LICENSE file for details
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.